#! /bin/bash

# Usage: $0 file1.pdf file2.pdf
#
#   compares file1.pdf and file2.pdf by rendering each page and using
#   the 'compare' ImageMagick utility
#
# Copyright 2007-2014 Sanjoy Mahajan.  Licensed under the GNU GPL version 3
# or (at your option) any later version.
#
# HISTORY
#   2014-06-22: Use mudraw instead of pdftoppm.  GPL v3+
#   2009-09-30: Fix capture of dB output; don't use a viewer; use pdftoppm
#   2007-01-15: First version
#

if [ -z "$DPI" ]; then
    DPI=72
fi
ext=png

if [ -z "$1" -o -z "$2" ]; then
  echo "Usage: $0 file1.pdf file2.pdf"
  exit 3
fi

# generate the many page images in a temporary directory
d=`mktemp -d`
mkdir -p $d/a $d/b
mudraw -r $DPI -g -o $d/a/%03d.$ext $1
mudraw -r $DPI -g -o $d/b/%03d.$ext $2
wait

# find the union of the page numbers (in case one pdf has more pages)
pages=`ls $d/{a,b}/*.$ext | sed "s%.*/\([0-9][0-9]*\).$ext%\1%" | sort -un`
# compare each page
for p in $pages ; do
  if ! [ -e "$d/a/$p.$ext" ] ; then
    echo "$p: missing from $1"
    continue
  fi
  if ! [ -e "$d/b/$p.$ext" ] ; then
    echo "$p: missing from $2"
    continue
  fi
  echo -n "$d/diff-$p.$ext $p "
  compare -metric mae $d/{a,b}/$p.$ext $d/diff-$p.$ext 2>&1
done